Adaptive reference updating for vibration-based structural health monitoring under varying environmental conditions

In this paper, a novel adaptive principal component analysis is proposed for identifying structural damage under varying environmental conditions (i.e., both stationary and non-stationary conditions). The proposed method is based on an adaptive reference scheme in multivariate statistical analysis. One crucial advantage of the proposed method is the ability of generative learning to capture the intrinsic behavior of the normal condition. The proposed method is numerically tested with noise in measurement under environmental variations. Its performance is compared with conventional methods (i.e., the fixed reference scheme). The numerical study demonstrates the superior performance of the proposed method for structural damage detection.